hermeneutic-gate

hermeneutic-gate is a skill for Claude Code, Codex from hermes-labs-ai/hermeneutic. It costs 46 tokens per session (350 once invoked), scanned A, original, Apache-2.0.

A pre-send checker for assistant drafts that looks for wording patterns linked to unsupported certainty, completion claims, broad statements, and unverified quality claims. It uses a local command-line tool and does not edit the draft or call an AI model.

In plain words
What is it for?
Use it to review drafts that contain numbers, completion language, words such as “every” or “always,” or summaries of work performed by another agent.
Why use it?
It provides a quick warning before a draft makes claims stronger than the available evidence. It is only a wording check, not proof that the underlying work is correct or complete.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to review drafts that contain numbers, completion language, words such as “every” or “always,” or summaries of work performed by another agent.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hermes-labs-ai/hermeneutic/hermeneutic-gate
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add hermes-labs-ai/hermeneutic --skill hermeneutic-gate
Clone the repo
git clone --depth 1 https://github.com/hermes-labs-ai/hermeneutic

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for hermeneutic-gate

README.md
[![agentmods](https://agentmods.dev/badge/skills/hermes-labs-ai/hermeneutic/hermeneutic-gate/github.svg)](https://agentmods.dev/skills/hermes-labs-ai/hermeneutic/hermeneutic-gate)
Your own site
<a href="https://agentmods.dev/skills/hermes-labs-ai/hermeneutic/hermeneutic-gate"><img src="https://agentmods.dev/badge/skills/hermes-labs-ai/hermeneutic/hermeneutic-gate/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for hermeneutic-gate

Your own site · 80×15
<a href="https://agentmods.dev/skills/hermes-labs-ai/hermeneutic/hermeneutic-gate"><img src="https://agentmods.dev/badge/skills/hermes-labs-ai/hermeneutic/hermeneutic-gate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 350 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00046 $0.00350
Opus 5 $0.00023 $0.00175
Sonnet 5 $0.00009 $0.00070
Haiku 4.5 $0.00005 $0.00035

Measured today against content hash b9d6625a58ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-16, from the pricing page.

Security

Grade A, and why

hermeneutic-gate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/hermeneutic-gate/SKILL.md · 37 lines

What it actually says

Hermeneutic gate

Use the installed hermeneutic CLI as a cheap, zero-LLM pre-flight check for assistant drafts. It catches fixed English surface patterns associated with completion overclaiming, relayed authority, unhedged certainty, scope expansion, and unsupported quality adjectives.

Workflow

  1. Identify the exact draft that is about to be sent.

  2. Run hermeneutic gate with the draft on standard input, for example:

    printf '%s' "$DRAFT" | hermeneutic gate
    
  3. Inspect the printed verdict as well as the exit code. A low-severity RISK is advisory and exits 0; medium- and high-severity RISK exits 1.

  4. If the draft is held, add the missing evidence, hedge the claim, or remove the unverifiable text before sending it.

The gate is advisory and does not edit the draft or call an LLM. Do not treat a pass as proof that a draft is correct, complete, safe, or free of novel drift. It checks English surface patterns only and does not replace human review.

Use this skill especially when the draft contains numeric claims, says that work is done or shipped, uses words such as “every” or “always”, or summarizes work completed by another agent.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. today First seen · 37 lines · 46 tokens per session scan A b9d6625a58ec

Subscribe to this mod's changes

hermeneutic-gate is a skill published in the GitHub repository hermes-labs-ai/hermeneutic (7 stars, last pushed yesterday), licensed Apache-2.0. It adds 46 tokens to every session and 350 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-16.

Related

Other skills, from other repositories

deepeval

DeepEval evaluation workflow for AI agents and LLM applications. TRIGGER when the user wants to evaluate or improve an AI agent, tool-using workflow, multi-turn chatbot, RAG pipeline, or LLM app; add evals; generate datasets or goldens; use deepeval generate; use deepeval test run; send results to Confident AI…

confident-ai/deepeval · 229 tokens

deepeval-otel

Export raw OpenTelemetry traces from an AI application to Confident AI's Observatory. TRIGGER when the user wants to send OpenTelemetry or OTLP traces/spans from an LLM app, agent, RAG pipeline, or chatbot to Confident AI; configure the Confident AI OTLP endpoint; set confident.span. or confident.trace. attributes…

confident-ai/deepeval · 226 tokens

deepeval-tracing

Instrument an AI application with DeepEval's native tracing so its behavior is visible in Confident AI. TRIGGER when the user wants to add DeepEval tracing or @observe to an LLM app, agent, RAG pipeline, or chatbot; wire a framework, model-provider, or vector-database integration (LangGraph, LangChain, OpenAI Agents…

confident-ai/deepeval · 208 tokens

tracely

Instrument AI agents with Tracely and turn their production traces into CI gates. Use when the user mentions Tracely, tracely-ai, tracelysdk, the tracely CLI, or asks to trace/observe an AI agent, add LLM evaluators or LLM-as-a-judge columns, debug why a trace or conversation isn't showing up, wire agent regression…

Jwuthri/Tracely-ai · 120 tokens

benchmark-radar

Find, inspect, and check AI benchmark records with the Benchmark Radar CLI. Use when a request needs benchmark discovery, details, recent Radar evidence, or local data health; do not assume why the user needs the results.

ktwu01/benchmark-radar · 48 tokens

deslop

Audit or apply evidence-backed, test-first subtractive cleanup for accumulated agent-created test bloat, verification theater, and defensive or fallback bloat while preserving independent external behavior. Invoke explicitly for semantic simplification, not generic refactoring.

MrZoyo/deslop-GPT · 49 tokens